FeaClip is method of time series representation based on feature extraction from run lengths (RLE) of bit-level (clipped) representation.
It extracts 8 key features from clipped representation.
There are as follows: $$repr = \{ max_1 - max. from run lengths of ones,$$
$$sum_1 - sum of run lengths of ones,$$
$$max_0 - max. from run lengths of zeros,$$
$$crossings - length of RLE encoding - 1,$$
$$f_0 - number of first zeros,$$
$$l_0 - number of last zeros,$$
$$f_1 - number of first ones,$$
$$l_1 - number of last ones \} .$$